Showing 2026Show all
3 papers · 1 filter
cs.RO2026
\textbf{PLATO}: \emph{Preintegration Learning from Accurate Trajectory Observations} for Neural Inertial Odometry
Haoying Li, Qihang Liu, Yifan Peng +2
Neural inertial odometry has demonstrated strong potential for motion estimation in challenging environments, yet inertial-only preintegration remains sensitive to IMU bias and unc…
cs.RO2026
A High-accuracy Event-based Underwater SLAM System
Yifan Peng, Qihang Liu, Haoying Li +3
While event cameras offer immense potential for underwater SLAM, existing Time Surface (TS)-based methods prove highly unreliable when deployed underwater. Fluctuating camera veloc…
cs.RO2026
Provably Guaranteed Polytopic Uncertainty Quantification for SLAM
Guangyang Zeng, Yulong Gao, Yuan Shen +4
In safety-critical robotics applications, guaranteed and practical uncertainty quantification (UQ) in perception is vital. Many existing works either offer no formal containment gu…